This module has been designed to help you develop your ability to conduct quantitative data analysis in the social sciences. The emphasis is not only on technical competence but also on understanding the principles behind the methods, as well as being able to competently interpret your results. We will be using real data with countless examples from across the social sciences (e.g., politics, economics, psychology, sociology, criminology, etc.) to learn about descriptive, exploratory, and inferential statistics. In doing so, we will cover topics such as data distributions, measurement, causality, correlation, regression, cluster analysis, spatial analysis, sampling and populations, and probability theory, using the R statistical programming language.
Module: EDC459
Title: Introduction to Quantitative Research
Credit Value: 15
Level: Postgraduate
Semester: Autumn
Module Leader: Dr. Calum Webb (c.j.webb@sheffield.ac.uk)
Time & Location: 12:00-14:50 in Geography Building, Computer Room B04 (Tuesdays, Week 1-6, 8-11)
You can bring your lunch.
Consultation & Feedback Hours: 10:00-11:00 Tuesdays (Week 1-12) and 15:00-16:00 Thursdays (Week 1-12)
Book through Google Calendar by clicking here.
You may book up to two appointment slots back-to-back (20 minutes). Please do so well in advance. When you book an appointment, it will be added to your Google Calendar automatically: I would strongly recommend linking your Google Calendar to your phone, laptop, and/or tablet.
On booking an appointment the invite will contain a Google Meets link by default. If you would like to meet face to face, please edit the appointment description or title to reflect this.
Please cancel your appointment as soon as possible if you can no longer attend. This means that other students will be able to take advantage of any freed up time.
This module will be taught in a computer room, but it is strongly recommended that you use your own laptop for exercises in R as you may not have access to university computers while working on your assessments.
Make sure you revisit these learning outcomes occasionally and take stock of what outcomes you feel you are reaching, which ones you are struggling with, and which ones you might need more support with.
By the end of the module, you should be able to demonstrate that you:
R to show patterns spatial patterns and concentration| Hours | ||
|---|---|---|
| Lectures & Activities | Each week will include a lecture and learning activities designed to provide an accessible introduction to the topic being covered. Activities might include gentle introductions to putting these concepts into practice in R. There may be recommended reading for each week. |
~10 |
| Data Lab Sessions | After each lecture we will work on a supported exercise in R in a group environment, learning how to apply the quantitative analysis methods we have learned in R with Rstudio. |
~20 |
Rather than giving ‘homework’ style tasks after each session that some people might be used to, you will often be expected to complete some preparation before each session: whether this is reading an book chapter, finishing a worksheet started in class, or watching a pre-recorded video. This is why it’s important for you to always check in advance what preparation needs to be completed.
Below are details on which topics will be covered in each week of the course, along with some reading on the topic. As the content becomes more complicated, I have chosen complementary readings where the first reading will cover the more theoretical aspects of the analytical method and the second reading will reinforce this theory and apply it in practice using R.
For comprehensive details of the suggested reading for each week, you should use the reading and resource list.
| Week | Topic | Recommended Reading |
|---|---|---|
| 1 | What is quantitative social science? | Powell, T. C. (2019). ‘Can Quantitative Research Solve Social Problems?’ & Mehmetoglu & Mittner (2022) Chapter 1, 2 & 3, Applied Statistics Using R |
| 2 | Types of quantification | Mehmetoglu & Mittner (2022) Chapter 4, Applied Statistics Using R |
| 3 | Relationships between variables | Mehmetoglu & Mittner (2022) Chapter 5, Applied Statistics Using R |
| 4 | Inference | Mehmetoglu & Mittner (2022) Chapter 6, Applied Statistics Using R |
| 5 | Causality | Goldthorpe, J. H. ‘Causation, Statistics and Sociology’ |
| 6 | Bivariate Linear Regression | Mehmetoglu & Mittner (2022) Chapter 7, Applied Statistics Using R |
| 7 | Reading Week | Catch up reading week |
| 8 | Multiple Linear Regression | Mehmetoglu & Mittner (2022) Chapter 8 & 9, Applied Statistics Using R |
| 9 | Logistic Regression | Mehmetoglu & Mittner (2022) Chapter 11, Applied Statistics Using R |
| 10 | Cluster Analysis | UC Business Analytics R Programming Guide ‘k-means Cluster Analysis’ (Available free online) ‘Hierarchical Cluster Analysis’ (Available free online) |
| 11 | Spatial Analysis | Imai, K. Chapter 5.3 ’Quantitative Social Science: An introduction (Available online through the library) |
You can find a detailed guide to recommended reading and independent learning activities in the Reading and Resources List page, which can be used in conjunction with the library resources list.
Conventionally, a course like this would have one set methods textbook. However, because R is a statistical programming language used across multiple disciplines with a very large number of additional libraries that are continually being developed, I would encourage you to experiment with different learning materials to find what works best for you. One author’s textbook chapter on data manipulation might, for example, not work as well for you as another’s. Further, you should feel free to use online resources if this helps you learn — because R is so widely used, you will find a lot of existing support.
With that said, there one textbook I would strongly recommend that you buy or access from the library throughout the module:
There is also a very short and accessible text I would recommend reading through to familiarise yourself with statistical and probability theory:
In the reading and resource list you will find the following:
R.This is a 15-credit module; therefore, it is expected it will require 150 study hours per student (including the above teaching hours). As a rough guideline this means you should expect to devote around 10 hours of study time per week to this module during a typical 15-week semester.
Everyone will be starting this module with different kinds of experience: some people might have never studied any kind of social statistics before and many will have never had to write code. I am unlikely to set you 8-10 hours of directed independent learning each week; it is up to you to identify your learning needs and use the resources provided to meet them. I am happy to help you with this process and provide suggestions if you find yourself stuck for things to do each week.
To ensure your independent learning is productive, you should regularly think about what parts of the module are challenging you. Examples of this might be:
R.You should then use the reading and resources list to plan some independent learning activities for that week.
This module will be assessed through two written data analysis projects using R to ensure that you have achieved the aims and learning outcomes of this module.
The first 1,000-word limit submission counts for 30% of your final module grade and is due before the winter break; the second 2,000-word limit submission counts for 70% of your grade and is due towards the end of January/early February. More details about these assessments along with exact deadlines will be made available as the module progresses, and can be found on the assessment Turnitin portal. The assessments will be posted on Blackboard well in advance of the relevant deadlines.
Please note that word limits will be enforced as per the student handbook. This means that you should not exceed the word limit. You will not be penalised for writing under the word limit, but should bear in mind that if you write substantially less than the limit you are unlikely to have included enough detail to demonstrate you have achieved all of the requirements for the assignment. Bibliographies (if necessary) are not included in word counts, but in-text citations are. You may choose whatever referencing format you wish (e.g., APA, Chicago, etc.), but please just be consistent throughout your submission.
Tables and graphs are not included in the word limit, though they should be used appropriately (there must be a good reason if long sections of text are included in a table). There are no limits on the number of tables or graphs you can use, but the content of all graphs and tables should be discussed and pertinent parts should be at least briefly described in the main text.
R code, comments, and output is also not included in the word limit, however, all pertinent information should always be in the main body of your assigment.1 Comments should be restricted to explaining the purpose of the code, and not used for communicating or interpreting the results.
Coursework must be submitted online through Blackboard/Turnitin and by no later than 12:00pm (noon) on the day of the deadline. Any unauthorised late submissions after midday on the day of the deadline will incur a penalty of up to 100%, as per the student handbook. Marked coursework will generally be returned within 3 working weeks. The pass mark for this module is 50% overall. Any change to assessment arrangements will be announced in Blackboard.
In the case of students who fail the assessment of this module, repeat assessment will be by a written, essay examination. Further instructions will be communicated to those who fail the module. Resit candidates must consult Blackboard for further information, up until the time of the reassessment, not merely in semester time. Resit marks will be capped at 50%.
Because coursework, unlike examinations, is not invigilated, the University lays down general rules so that everyone is clear about what is acceptable practice. These rules are set out formally in the regulations for non-invigilated examinations in Part I of the University Calendar. Further information can be found in the University’s Academic Integrity webpages.
The basic principle underlying the preparation of any piece of academic work is that the work submitted must be your own work. Plagiarism, submitting bought or commissioned work, double submission (or self-plagiarism), collusion and fabrication of results are not allowed because they violate this principle. Similarly, inappropriate use of generative AI is considered misconduct. Rules about these forms of cheating apply to all assessed and non-assessed work. More details can be found in the student handbook.
Any form of academic misconduct is treated as a serious academic offence and action may be taken under the Discipline Regulations. Where academic misconduct is found to have been used, the University may impose penalties ranging from awarding a grade of zero for the assignment through to expulsion from the University in extremely serious cases.
The University subscribes to a national plagiarism detection service called Turnitin which helps academic staff identify the original source of material submitted by students. It is also a resource, which can help tutors to advise students on ways of improving their referencing techniques. Your work will be checked by this service and results will be assessed by the marker.
Generative AI detection tools are not used at the University of Sheffield. This is due to concerns over their error rates and the potential for both false positives and false negatives when scanning for potential use of Generative AI. Rather, we require all students complete an Acknowledge, Describe, and Evidence form for every assessment they submit, and any concerns raised around inappropriate use of generative AI are reviewed by an Academic Misconduct Officer.
Usage of generative AI constitutes academic misconduct when content that was created using generative AI technologies is presented as your own work. This means when generative AI has been used to create a part, or the entirety, of an assessment submission, either,
In the first instance, a good rule to follow is: ‘if you copied output from a generative AI model directly into your assignment, this probably constitutes academic misconduct’. In addition, if you know there is output from a generative AI tool that you included in your assessment but did not acknowledge, describe, and evidence this in your assessment cover sheet, this would be considered academic misconduct. If your use of generative AI is replacing, rather than reinforcing, your learning, this probably constitutes academic misconduct.
Generative AI outputs should never be used as sources for assessment and you should never cite anything from a generative AI tool. This is because content generated by AI tools is not reliable and is usually non-recoverable and non-reproducible at a later date, so it cannot be retrieved from a link or citation. You must check any module specific guidance before using generative AI on a module.
Policies on coursework extensions and extenuating circumstances can be found in the Student Handbook. If you wish to apply for a coursework extension, you should contact the Learning & Teaching Support Team in the first instance (smi@sheffield.ac.uk), in advance of the coursework deadline, and include the relevant Extenuating Circumstances Form plus medical certification if appropriate. Your application will then be considered, and the outcome communicated to you as soon as possible.
Please note that module leaders cannot grant extensions.
There will be feedback on your understanding of this module during the course of module delivery. Students will receive individual written feedback on each formal assessment.
In addition, the module will use a Blackboard discussion page where students can seek feedback on individual issues both from the teaching staff and from fellow students.
Feedback on your understanding as the module progresses as well as on all the elements of module assessment can be obtained at any time by using consultation and feedback hours.
We always welcome your comments and feedback as the module progresses, and informal evaluation of this kind will take place throughout the module. Students will also be invited to complete an anonymised module evaluation form towards the end of the module. These will be reviewed by the Director of Education and the module leader. Any changes made to the module as an outcome of student evaluation will be communicated to new/future cohorts of students and in the following year’s module Blackboard pages.
You can use the Rstudio wordcountaddin Add In to get an accurate word count of your assignment if it is written in Rmarkdown, which you are encouraged to use (requires installation with devtools: devtools::install_github("https://github.com/benmarwick/wordcountaddin")).↩︎